activity
20242026
collaborators

12 papers

cs.LG2026

Alignment Defends LLMs from Property Inference Attacks

Pengrun Huang, Chhavi Yadav, Ruihan Wu +1

Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties. Recent work has shown that such dataset-l…

cs.CR2026

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…

cs.AI2025

Embodied AI Agents: Modeling the World

Pascale Fung, Yoram Bachrach, Asli Celikyilmaz +18

This paper describes our research on AI agents embodied in visual, virtual or physical forms, enabling them to interact with both users and their environments. These agents, which…

cs.CL2025

Learning-Time Encoding Shapes Unlearning in LLMs

Ruihan Wu, Konstantin Garov, Kamalika Chaudhuri

As large language models (LLMs) are increasingly deployed in the real world, the ability to ``unlearn'', or remove specific pieces of knowledge post hoc, has become essential for a…

cs.LG2025

Can We Infer Confidential Properties of Training Data from LLMs?

Pengrun Huang, Chhavi Yadav, Kamalika Chaudhuri +1

Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets to support applications in fields such as healthcare, finance, and law. These fine-tuning datas…

cs.CL2025

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun Hsu +9

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of i…